-
Tencent
- Chengdu, China
Stars
- All languages
- ActionScript
- Ada
- Assembly
- C
- C#
- C++
- CMake
- CSS
- ChucK
- Clojure
- Cuda
- Dart
- Emacs Lisp
- Erlang
- GAP
- Go
- HTML
- Hack
- Haskell
- Java
- JavaScript
- Julia
- Jupyter Notebook
- Kotlin
- Lua
- MATLAB
- MDX
- Makefile
- NewLisp
- Objective-C
- OpenEdge ABL
- PHP
- Perl
- PureBasic
- Python
- R
- Ruby
- Rust
- SCSS
- Scala
- Shell
- Svelte
- Swift
- TeX
- TypeScript
- XSLT
A Systematic and Unified Reproducible Evaluation Toolkit (SURE). Easy to use and integrate like a plugin. Build your evaluation pipeline here!
A Strong Agentic Framework for Model Adaptation and Auto-Evaluation
Code and Data for "A Benchmark Dataset and Comparative Evaluation of Phonemized and Romanized Urdu for Text-to-Speech"
The offical implementation of DeMix (Decouple Searching from Training: Scaling Data Mixing via Model Merging for Large Language Model Pre-training)
A toolkit for speaker diarization.
DeepSeek Harness: Everything is a Plugin.
A TTS that fits in your CPU (and pocket)
Build Real-Time Knowledge Graphs for AI Agents
JevBench by Benchmark Heaven: benchmark and leaderboard for AI decision models, measuring typed decision accuracy, calibration, latency and cost.
Open, Jev-compatible System One decision server on DiffusionGemma
Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.
Corpus of oral arguments (recorded speech + official transcripts) of the United States Supreme Court
SpeechIO Leaderboard: a large, robust, comprehensive, benchmarking platform for Automatic Speech Recognition.
Crowd Sourced Emotional Multimodal Actors Dataset (CREMA-D)
Open-source text-to-speech model from KRAFTON trained exclusively on public speech data, with curated datasets and reproducible training support.
Metadata and versioning details for the Common Voice dataset
LibriTTS-P: A Corpus with Speaking Style and Speaker Identity Prompts for Text-to-Speech and Style Captioning
Reference BLEU implementation that auto-downloads test sets and reports a version string to facilitate cross-lab comparisons
a lightweight speech processing toolkit based on Pytorch and (Py)Kaldi